antirez: Reading AI code is no longer feasible — he now trusts tests and QA instead
antirez · x · 2026-09-27
In an exchange with mitsuhiko, Redis creator antirez argues that AI now produces 10-20k lines of code per day, far beyond what anyone can review by reading. Instead of building confidence by reading the code, he relies on proxies: how the program works and feels, plus extensive QA and tests. mitsuhiko says he hasn't made that transition yet, lacking confidence in the output of Astra.
More from coding & agent
- TypeSafe ships official skill teaching Claude Code to batch Jev calls, cutting bills 12.2x — anselm · 2026-09-27
- World's fastest panel QR factorization on B200: how a GPU MODE contestant cracked chained dependencies — A_K_Nain · 2026-09-27
- Graph Engineering: Author Finds Agent's Self-Checking Was Lying to Him — blaizedsouza · 2026-09-27
- One prompt in OpenCode builds a full 3D solar system observatory with themes — JaynitMakwana · 2026-09-27
- Stop building agents as a straight line: the 90-second test to cut fake dependencies — blaizedsouza · 2026-09-27
- Digital Apprentice framework: agents earn autonomy through per-skill authorization gates — blaizedsouza · 2026-09-27